INDEX

Explanations

phrases indicating intention or purpose in discussions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ſelf

-0.72

ſelves

-0.71

XmlAccessType

-0.67

 itſelf

-0.64

 ſmall

-0.63

 paſſ

-0.60

 ſeveral

-0.57

 Houſe

-0.57

 greateſt

-0.54

 ſch

-0.54

POSITIVE LOGITS

 Dafür

0.83

 hierfür

0.68

GEBURTSDATUM

0.62

 daarvoor

0.62

 dafür

0.61

ofür

0.60

为此

0.49

Dazu

0.47

 Dazu

0.46

ために

0.44

Activations Density 0.413%

phrases indicating intention or purpose in discussions

No Comments

No Known Activations